Picture for Jun Wan

Jun Wan

FA^{3}-CLIP: Frequency-Aware Cues Fusion and Attack-Agnostic Prompt Learning for Unified Face Attack Detection

Add code
Apr 01, 2025
Viaarxiv icon

Mixture-of-Attack-Experts with Class Regularization for Unified Physical-Digital Face Attack Detection

Add code
Apr 01, 2025
Viaarxiv icon

Recover and Match: Open-Vocabulary Multi-Label Recognition through Knowledge-Constrained Optimal Transport

Add code
Mar 19, 2025
Viaarxiv icon

Unifying Two Types of Scaling Laws from the Perspective of Conditional Kolmogorov Complexity

Add code
Jan 12, 2025
Viaarxiv icon

Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer

Add code
Dec 01, 2024
Figure 1 for Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer
Figure 2 for Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer
Figure 3 for Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer
Figure 4 for Precise Facial Landmark Detection by Dynamic Semantic Aggregation Transformer
Viaarxiv icon

Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models

Add code
Oct 25, 2024
Figure 1 for Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
Figure 2 for Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
Figure 3 for Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
Figure 4 for Rethinking Visual Dependency in Long-Context Reasoning for Large Vision-Language Models
Viaarxiv icon

La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection

Add code
Aug 23, 2024
Figure 1 for La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection
Figure 2 for La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection
Figure 3 for La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection
Figure 4 for La-SoftMoE CLIP for Unified Physical-Digital Face Attack Detection
Viaarxiv icon

A Unified Framework for Iris Anti-Spoofing: Introducing IrisGeneral Dataset and Masked-MoE Method

Add code
Aug 19, 2024
Figure 1 for A Unified Framework for Iris Anti-Spoofing: Introducing IrisGeneral Dataset and Masked-MoE Method
Figure 2 for A Unified Framework for Iris Anti-Spoofing: Introducing IrisGeneral Dataset and Masked-MoE Method
Figure 3 for A Unified Framework for Iris Anti-Spoofing: Introducing IrisGeneral Dataset and Masked-MoE Method
Figure 4 for A Unified Framework for Iris Anti-Spoofing: Introducing IrisGeneral Dataset and Masked-MoE Method
Viaarxiv icon

C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval

Add code
Aug 19, 2024
Figure 1 for C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval
Figure 2 for C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval
Figure 3 for C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval
Figure 4 for C${^2}$RL: Content and Context Representation Learning for Gloss-free Sign Language Translation and Retrieval
Viaarxiv icon

SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition

Add code
Jul 30, 2024
Figure 1 for SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
Figure 2 for SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
Figure 3 for SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
Figure 4 for SSPA: Split-and-Synthesize Prompting with Gated Alignments for Multi-Label Image Recognition
Viaarxiv icon